© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5581
    Prev
    Next
    INDEX
    Explanations

    the phrase "square root" and instances of the preposition/particle "de"

    oai_token-act-pair · gemini-2.0-flash

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -1.01
    fromnode
    -0.92
     تضيفلها
    -0.89
    InjectAttribute
    -0.88
    Tikang
    -0.82
     onOptions
    -0.82
     Audiodateien
    -0.81
     виправивши
    -0.78
    interopRequire
    -0.77
     Réponses
    -0.76
    POSITIVE LOGITS
    <bos>
    1.76
    ↵↵
    0.60
    1
    0.59
    I
    0.55
    <strong>
    0.54
    B
    0.54
    We
    0.53
    2
    0.53
    3
    0.52
    #
    0.52
    Activations Density 0.433%

    No Known Activations